gpt-live-transcribe

transcriptionproprietary

GPT Live Transcribe is a streaming speech-to-text model for applications that need low-latency transcript deltas from live audio. It supports tunable latency, unstructured context, keyword hints, and multiple language hints.

Intelligence
Speed
Input price
$0/1M tokens
Output price
$0/1M tokens

Capabilities

Infrastructure
Streaming

Details

Provider Vercel AI Gateway
Creator OpenAI
Family—
Licenseproprietary
Statusactive
Typetranscription
Input modalitiesspeech, text
Output modalitiestext
Open weightNo
Parameters—
Architecture—
Languages—
Release date—
Sourceofficial

Pricing

Input
$0
Output
$0
Cache write
—
Cache read
—
Batch in
—
Batch out
—

API

GET/v1/models/vercel/openai/gpt-live-transcribe